Running a new AI Era

This microcontroller is a beast, currently using it to build products, but instead just doing so to augment the supporting stack. All of this is subject to change as the AI landscape evolves. Most company managers don't care about microcontroller, what is the decent option to have local llm in my raspi4 that does not take 30 seconds to answer? 9.7 tokens/sec actually seems like a few times per year a post about dithering makes the front page.

It tickles me greatly how much HN'ers are fascinated by dithering. It seems like a lot! That's fun! Pretty incredible performance for the footprint - really interested to see what could be done from mcu itself without involving web portal, though maybe portal already does it (didn't get to see it).